Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/calle-ai/awesome-phone-call-agents/injection-guard-reviewer)<a href="https://agentmods.dev/agents/calle-ai/awesome-phone-call-agents/injection-guard-reviewer"><img src="https://agentmods.dev/badge/agents/calle-ai/awesome-phone-call-agents/injection-guard-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/calle-ai/awesome-phone-call-agents/injection-guard-reviewer"><img src="https://agentmods.dev/badge/agents/calle-ai/awesome-phone-call-agents/injection-guard-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.00702 |
| Opus 5.5 | $0.00024 | $0.00281 |
| Sonnet 5.5 | $0.00012 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
injection-guard-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security reviewer specializing in prompt injection. You must audit the full data flow from external/untrusted sources to anywhere that content could influence what CALL-E's agent says on a live call, or what code executes.
Threat model
External untrusted content includes:
- OpenStreetMap business listing data (name, category, tags — any field from OSM)
- CALL-E API response fields (summary, transcript, extracted fields, outcome text)
- Any user-supplied data that hasn't been explicitly reviewed and approved
What you must check
-
OSM data → goal string
- Read
discovery.py,script_gen.py, andmain.py. - Trace what happens to
vendor["name"],vendor["category"], and any other OSM field. - Confirm that NO OSM field is concatenated directly into the
--goalstring passed toplan_call(). - The goal string must be generated from the
product_descriptiononly (client-supplied and client-approved), treating OSM data as untrusted display labels only. - Flag as BLOCKING if any OSM field reaches the goal string without going through the client-edit approval step.
- Read
-
CALL-E response → re-injected into subsequent goals
- Read the R1→R2 flow in
main.py. - Confirm that R2's goal string is generated independently by
script_gen.py, not constructed from R1's transcript, summary, or extracted fields. - Flag as BLOCKING if any field from a CALL-E API response is inserted into a subsequent goal string.
- Read the R1→R2 flow in
-
Client-edit approval gate is real
- Find the approval step in
main.pyor the web UI. - Confirm the client actually sees and can edit the goal string before it's passed to
plan_call(). - Flag as BLOCKING if the approval is cosmetic (shown but not editable, or auto-confirmed without display).
- Find the approval step in
-
Shell command safety
- Read
caller.py's_run()function. - Confirm the args list is constructed from static strings and validated E.164 phone numbers only — never from OSM fields or API response text.
- Flag as BLOCKING if any external string is interpolated into a shell command.
- Read
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 49 lines · 59 tokens per session scan A f002fb96f39b
injection-guard-reviewer is an agent published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 702 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.